
Ultimate access to all questions.
Updated: April 2026
This page ranks LLMs by score on Databricks Certified Data Engineer - Associate exam-like questions using a consistent, repeatable benchmark. Use it to compare models on the same quiz set and choose which one to rely on for your study workflow.
Ranked by benchmark score (0–100) for this certification quiz set.
| Rank | Model | Input Price | Output Price | Score | Correct | Total | Updated |
|---|---|---|---|---|---|---|---|
| 1 | gemini-3-flash | $0.50 | $3.0 | 95.6 | 43 | 45 | 2 days ago |
| 2 | gemini-3.1-pro | $2.0 | $12 | 95.6 | 43 | 45 | 2 days ago |
| 3 | gpt-5.4 | $2.5 | $15 | 93.3 | 42 | 45 | 2 days ago |
| 4 | glm-5 | $0.80 | $2.6 | 93.3 | 42 | 45 | 2 days ago |
| 5 | gemma-4-31b-it | $0.14 | $0.40 | 91.1 | 41 | 45 | 2 days ago |
| 6 | kimi-k2.5 | $0.50 | $2.8 | 91.1 | 41 | 45 | 2 days ago |
| 7 | gpt-5.4-mini | $0.75 | $0.45 | 91.1 | 41 | 45 | 2 days ago |
| 8 | mimo-v2-pro | $1.0 | $3.0 | 91.1 | 41 | 45 | 2 days ago |
| 9 | qwen3.6-plus | $0.50 | $3.0 | 88.9 | 40 | 45 | 2 days ago |
| 10 | deepseek-v3.2 | $0.26 | $0.38 | 88.9 | 40 | 45 | 2 days ago |
| 11 | gpt-oss-120b | $0.039 | $0.19 | 86.7 | 39 | 45 | 2 days ago |
| 12 | minimax-m2.7 | $0.25 | $1.2 | 75.6 | 34 | 45 | 2 days ago |
We create an exam-like quiz set, verify the correct answers, ask each model to answer and explain, extract the model’s final answers, and compute a benchmark score for the certification.
The score is a benchmark result for this certification’s quiz set. Higher is better, and scores are normalized to a 0–100 scale.
Rankings can change when models are updated, prompts or extraction improve, or new benchmark runs are added. This page shows the oldest recorded benchmark run per model to keep comparisons stable.
Use it as a starting point: prioritize models with higher scores, then validate with your own workflow (answer accuracy, explanation clarity, and consistency on your weak topics).